A novel method for clustering cellular data to improve classification

Many fields,such as neuroscience,are experiencing the vast prolife ration of cellular data,underscoring the need fo r organizing and interpreting large datasets.A popular approach partitions data into manageable subsets via hierarchical clustering,but objective methods to determine the appropriate classification granularity are missing.We recently introduced a technique to systematically identify when to stop subdividing clusters based on the fundamental principle that cells must differ more between than within clusters.Here we present the corresponding protocol to classify cellular datasets by combining datadriven unsupervised hierarchical clustering with statistical testing.These general-purpose functions are applicable to any cellular dataset that can be organized as two-dimensional matrices of numerical values,including molecula r,physiological,and anatomical datasets.We demonstrate the protocol using cellular data from the Janelia MouseLight project to chara cterize morphological aspects of neurons.

Classification of Multi-User Chirp Modulation Signals Using Wavelet Higher-Order-Statistics Features and Artificial Intelligence Techniques

Higher order statistical features have been recently proved to be very efficient in the classification of wideband communications and radar signals with great accuracy. On the other hand, the denoising properties of the wavelet transform make WT an efficient signal processing tool in noisy environments. A novel technique for the classification of multi-user chirp modulation signals is presented in this paper. A combination of the higher order moments and cumulants of the wavelet coefficients as well as the peaks of the bispectrum and its bi-frequencies are proposed as effective features. Different types of artificial intelligence based classifiers and clustering techniques are used to identify the chirp signals of the different users. In particular, neural networks (NN), maximum likelihood (ML), k-nearest neighbor (KNN) and support vector machine (SVMs) classifiers as well as fuzzy c-means (FCM) and fuzzy k-means (FKM) clustering techniques are tested. The Simulation results show that the proposed technique is able to efficiently classify the different chirp signals in additive white Gaussian noise (AWGN) channels with high accuracy. It is shown that the NN classifier outperforms other classifiers. Also, the simulations prove that the classification based on features extracted from wavelet transform results in more accurate results than that using features directly extracted from the chirp signals, especially at low values of signal-to-noise ratios.

STATISTICAL CLASSIFICATION AND CHARACTERISTICS ANALYSIS OF BINARY TROPICAL CYCLONES OVER THE WESTERN NORTH PACIFIC OCEAN

Using the 1949-2007 western North Pacific tropical cyclones (TCs) best-track data archived at the Shanghai Typhoon Institute of China Meteorological Administration for the western North Pacific from 1949 to 2007,both the characteristics of binary and multiple TCs and samples of interactions among TCs and multi-TCs are identified and statistically analyzed.According to the various features of individual TC tracks and interacting tracks,seven distinct types are proposed to describe the binary system of TCs and their interaction samples.The mean trajectories of the west and east component of binary TCs in each type are obtained using a new cluster analysis technique.These types are then analyzed in terms of landfall process,occurrence seasonality,coexistent lifetime,especially the large-scale patterns of atmospheric circulation.Finally,typical steering flows and conceptual models of the binary TCs at different phases are established based on six-hourly flow maps of the binary system and the averages are determined of the mean steering flow of ten representative binary TCs.Then,typical steering flows and conceptual models at the beginning,middle and final phase in each type are established to describe the large-scale circulation patterns of the binary system interaction types.

A statistical approach to classification of keratoconus

INTRODUCTIONThe front portion of the eye consists of a transparent layer called the cornea.The cornea is an important optical component for vision and plays a role in the specific refraction of the eye.The cornea normally has convexity but the amount of protrusion progressively increases in patients with keratoconus.In other words,the cornea prolapses forward.Keratoconus is a bilateral,typically asymmetric and non-inflammatory degeneration of the cornea caused by corneal protrusion as a result of progressive thinning of the corneal stroma.Corneal thinning generally occurs in the inferior,inferotemporal or central regions of the cornea.

The Classification of Statistically Recursive Sets

The main aim of this paper is to make a classification of random sets K m(ω) constructed in theorem 2.1 and theorem 2.1' in . We provide five criterions for the classification. Many kinds of random sets such as Hawkes constructed in , Graf constructed in and Mauldin constructed in are the special cases of K m(ω) constructed in ,and then these random sets belong to some model respectively according to our classification.

Image Classification using Statistical Learning Methods

In general, digital images can be classified into photographs, textual and mixed documents. This taxonomy is very useful in many applications, such as archiving task. However, there are no effective methods to perform this classification automatically. In this paper, we present a method for classifying and archiving document into the following semantic classes: photographs, textual and mixed documents. Our method is based on combining low-level image features, such as mean, Standard deviation, Skewness. Both the Decision Tree and Neuronal Network Classifiers are used for classification task.

Statistical Features and Traditional SA-SVM Classification Algorithm for Crack Detection

In recent years, the interest in damage identification of structural components through innovative techniques has grown significantly. Damage identification has always been a crucial concern in quality assessment and load capacity rating of infrastructure. In this regard, researchers focus on proposing efficient tools to identify the damages in early stages to prevent the sudden failure in structural components, ensuring the public safety and reducing the asset management costs. The sensing technologies along with the data analysis through various techniques and machine learning approaches have been the area of interest for these innovative techniques. The purpose of this research is to develop a robust method for automatic condition assessment of real-life concrete structures for the detection of relatively small cracks at early stages. A damage identification algorithm is proposed using the hybrid approaches to analyze the sensors data. The data obtained from transducers mounted on concrete beams under static loading in laboratory. These data are used as the input parameters. The method relies only on the measured time responses. After filtering and normalization of the data, the damage sensitive statistical features are extracted from the signals and used as the inputs of Self-Advising Support Vector Machine (SA-SVM) for the classification purpose in civil Engineering area. Finally, the results are compared with traditional methods to investigate the feasibility of the hybrid proposed algorithm. It is demonstrated that the presented method can reliably detect the crack in the structure and thereby enable the real-time infrastructure health monitoring.

Statistical Methods for Classification of Medicinal Plants

Statistical classification methods are frequently applied to analyze metabolomics data, especially from medicinal plants. Combined with variable selection techniques, we are able to identify marker candidates, which can be used to discriminate the group to which unknown subjects belong. After preprocessing, such as outlier checking, normalization, missing value imputation and transformation, we then mainly utilized four novel classification methods： RF （random forest）, NSC （nearest shrunken centroid）, PLS-DA （partial least square discriminant analysis） and SAM （significant analysis ofmicroarrays）. Each method has its own device to measure the importance of single metabolite, so that, it is probable to choose highly ranked metabolites, which show the best prediction accuracy. Adapting above strategy, we have successfully analyzed several kinds of metabolomics data including Panax ginseng, Lespedeza species, Anemarrhean asphodeloides and Gastrodia elata.

CLASSIFICATION OF MPSK SIGNALS USING CUMULANT INVARIANTS

A new feature based on higher order statistics is proposed for classification of MPSKsignals, which is invariant with respect to translation (shift), scale and rotation transforms of MPSK signal constellations, and can suppress additive color or white Gaussian noise. Application of the new feature to classification of MPSK signals, at medium signal-to-noise ratio with specified sample size, results in high probability of correct identification. Finally, computer simulations and comparisons with existing algorithms are given.

Classification of marine diatoms using pigment ratio suites

Diatoms are widely distributed in many temperate areas and some species frequently form extensive blooms in spring. Hence, monitoring the variations of specific genera or species of diatoms is necessary for studying phytoplankton population dynamics in marine ecosystems. To test whether pigment ratios can be used to identify diatoms at a below-class taxonomic level, we analyzed 14 species/strains of diatoms isolated from Chinese seas using high performance liquid chromatography （HPLC）. We normalized all pigment concentrations to total chlorophyll a to calculate the ratios of pigment to chlorophyll a, and calculated the ratios between accessory pigments （or pigment sums）. Cluster analysis indicated that these diatoms could be classified into four clusters in terms of three accessory pigment ratios： chlorophyll c2： chlorophyll Cl, fucoxanthin：total chlorophyll c and diadinoxanthin：diatoxanthin. The classification results matched well with those of biological taxonomy. To test the stability of the classification, pigment data from one species, cultured under different light intensities, and five new species/strains were calculated and used for discriminant analysis. The results show that the classification of diatom species using pigment ratio suites was stable for the variations of pigment ratios of species cultured in different light intensities. The introduction of new species, however, may confuse the classification within the current scheme. Classification of marine diatoms using pigment ratio suites is potentially valuable for the fine chemotaxonomy of phytoplankton at taxonomic levels below class and would advance studies on phytoplankton population dynamics and marine ecology.

Applications of Hyperspectral Remote Sensing in Ground Object Identification and Classification

Hyperspectral remote sensing has become one of the research frontiers in ground object identification and classification. On the basis of reviewing the application of hyperspectral remote sensing in identification and classification of ground objects at home and abroad. The research results of identification and classification of forest tree species, grassland and urban land features were summarized. Then the researches of classification methods were summarized. Finally the prospects of hyperspectral remote sensing in ground object identification and classification were prospected.

Random forest algorithm for classification of multiwavelength data

We introduced a decision tree method called Random Forests for multiwavelength data classification. The data were adopted from different databases, including the Sloan Digital Sky Survey （SDSS） Data Release five, USNO, FIRST and ROSAT. We then studied the discrimination of quasars from stars and the classification of quasars, stars and galaxies with the sample from optical and radio bands and with that from optical and X-ray bands. Moreover, feature selection and feature weighting based on Random Forests were investigated. The performances based on different input patterns were compared. The experimental results show that the random forest method is an effective method for astronomical object classification and can be applied to other classification problems faced in astronomy. In addition, Random Forests will show its superiorities due to its own merits, e.g. classification, feature selection, feature weighting as well as outlier detection.

Application of Statistical Methods and GIS for Downscaling and Mapping Crop Statistics Using Hypertemporal Remote Sensing

To sustain the management of natural resources, land use and land cover （LULC） should be spatially mapped and temporally monitored using GIS. For large areas, conventional methods are laborious. Alternatively, remote sensing can be used for LULC mapping and monitoring. Normalized differential vegetation index （NDVI） is the most used vegetation index for crop identification and phenology. For agricultural areas, crop statistics are estimated yearly at regional level following administrative units. However, these statistics are not informing about spatial extent of these crops within administrative units; such information is crucial for crop monitoring. The main objective of this research was to fill the gap, based on statistical methods and GIS, by adding spatial information to crop statistics by analyzing temporal NDVI profiles. The study area covers 1300 km2. Data consist of 147 decadal Spot Vegetation NDVI images. Crop statistics were compiled on seasonal basis and aggregated to different administrative levels. Images were processed using an unsupervised classification method. A series of classification runs corresponding to different numbers of clusters were used. Using stepwise multiple linear regression, cropped areas from agricultural statistics were related to areas of each NDVI profile cluster. Estimated regression coefficients were used to generate maps showing cropped fractions by map units. The optimal number of clusters was 18. Similar profiles were merged leading to eight clusters. The results show that, for example, rice was grown, in autumn, on 50% of the area of map-units represented by NDVI-profile group 4 and 75% of the area of group 7 while it was grown, in spring, on 2, 69 and 25% of areas of NDVI-profile groups 2, 61 and 7, respectively. Regression coefficients were used to generate map of crops. This research illustrates the benefit of integrating statistical methods, GIS, remote sensing and crop statistics to delineate NDVI profile clusters with their corresponding agricultural land cover map units and to link these statistics to geographical locations. These map units can be used as a reference for future monitoring of natural resources, in particular crop growth and development and for forecasting crop production and/or yield and stresses like drought.

Application of Multi-Attribute Crossplots to Tight Gas in X Area, Western China

The gas-bearing reservoir in X area is mainly the tight sandstone reservoir characterized by low porosity and permeability, frequently lateral variation and poor connectivity of single sand. The previous research results reveal that the general seismic attributes analysis cannot meet the requirement of fluid identification. This is because the relationship between seismic attributes and their implication is uncertain and ambiguous, which decreases the precision of both reservoir prediction and fluid identification. To overcome the problem, multi-attribute crossplot technology is proposed from the mathematical statistical point of view rather than the correspondence between the seismic attributes and their geological implication. In this method, the wells which have the same statistical law are classified firstly, and then all the interest wells are retained while the wells beyond the statistical law are eliminated, and the seismic attributes sensitive to the same types of eliminated wells are optimized and used to generate crossplots. The nonzero area of their crossplots results just predicts the potential distribution. The discontinuity of subsurface geological conditions results in the non-continuous shape and the seismic bin lead to the mosaic form. The optimization of sensitive attributes relative to the same types of wells is independent from each other, and thus the order of attributes in crossplots does not affect the final prediction results. This method is based on the statistical theory and suitable for the areas such as the study area abundant of lots of well data. Application to X area proves the effectiveness of this method and predicts plane distribution about different types of gas production. Due to the effect of faults and other geological factors, the partition prediction results using multi-attribute crossplots reach 95% of coincidence which is obviously and far higher than the results of the whole area. The final prediction results show that the potential areas with medium and high gas production are mainly concentrated in the northern part of the study area, where lots of development research will be strengthened.

中国大健康产业统计分类与产业规模再测算

由于产业间深度融合,新业态、新模式持续涌现,健康产业的边界不断拓展,原有的健康产业统计分类已不能满足大健康产业的统计需要,官方统计也未测算出健康产业增加值,无法全面、及时反映大健康产业的发展状况。因此,文章首先在健康产业基础上从供给和需求角度界定并拓展大健康产业的内涵及外延;其次,在《健康产业统计分类(2019)》的基础上,基于国民经济核算理论,引入“大健康总产品”概念,聚焦“全生命周期”和“全人群”两个着力点,从全产业链产品供给及全口径人群健康需求两个视角探讨大健康产业统计分类标准,补充和完善大健康产业统计分类;最后,依据现有的投入产出表、经济普查及统计年鉴数据,计算各行业的大健康分离系数,据此推算我国大健康产业及健康服务业增加值。结果显示:2018年我国大健康产业增加值为10.27万亿元,其中健康服务业增加值为7.04万亿元,预测2020年、2030年健康服务业增加值分别为8.46万亿元、21.27万亿元,基本符合《“健康中国2030”规划纲要》对健康服务业发展规模的预期。

河南省近30年分级短时强降水时空分布特征分析

利用1992-2021年4-10月河南省101个台站逐时降水资料并结合地形,统计分析了河南省不同量级短时强降水的时空演变特征及其与地形的关系。结果表明:(1)R1h≥20 mm·h^(-1)的短时强降水和3个不同量级的短时强降水频次分布均呈东多西少的分布特征,短时强降水和[20 mm·h^(-1),50mm·h^(-1))量级的短时强水出现的频次均呈南多北少的分布特征,[50 mm·h^(-1),80 mm·h^(-1))量级的短时强水出现的频次表现为南北之间差别不大,而[80 mm·h^(-1),+∞)量级的短时强水出现的频次呈南少北多的分布特征。各月短时强降水频次的空间分布为东多西少,7月、8月和10月南北之间差别不大,其他月份呈南多北少的分布特征。(2)短时强降水年际变化差别大,月变化呈单峰型,6月下旬-8月上旬是各量级短时强降水多发时段。(3)短时强降水频次日变化分布呈双峰型,16-21时的发生频次最高,00-05时的次之,09-14时的最低。6-8月短时强降水频次的日变化特征呈双峰型,其他月份的双峰特征不明显。4-10月16-21时出现日峰值的站点最多,00-05时的次之,空间分布呈东大西小、南大北小的分布特征,各月00-05时出现日峰值的站数最多,16-21时的次之。(4)最大雨强和短时强降水量的占比均呈东高西低、北高南低的分布特征。(5)短时强降水的空间分布、日变化空间分布、最大雨强高值区和短时强降水量占比等均与河南省地形关系密切,地形对短时强降水有增(减)幅作用。

国际标准行业分类的演化进展、标准更新与中国启示

行业分类的科学建立、及时更新和有效实施对国民经济发展具有重要意义。在行业分类体系中,联合国发布的《国际标准行业分类》(ISIC)最具影响力,是各国行业分类标准制定的风向标。以ISIC的国际进展为研究主线,系统梳理ISIC的发展历程,从差异性角度剖析ISIC各个版本在分类原则、分类结构、符号体系等方面的演变规律,并归纳总结最新版ISIC Rev.5的基本结构和主要变化。之后,结合我国经济发展现状和统计工作需要,分析ISIC更新对我国国民经济行业分类标准修订工作的启示,以期探寻我国国民经济行业分类的优化路径。

融合概率类别特征增强的短文本分类

对短文本所含信息量缺乏而导致分类准确度难以提升的问题进行研究,提出一种融合概率类别特征增强的短文本分类网络模型FT_BDCNN。将N-gram处理后产生的N元词典通过TF-IDF分离出具有概率类别区分度的特征信息(FT模块);将向量化表示后的文本信息输入到改进后的特征提取模块中;将两个模块的输出进行特征融合,完成文本分类。实验结果表明,所提模型在THUCNews数据集上的F1值达到91.91%。FT模块可以与现有分类模型进行融合,提升模型的分类性能。

水上交通事故分类统计比较研究

通过水上交通事故分类统计比较研究,进一步规范水上交通事故的统计范围和边界,细化统计分类,为事故成因分析提供详实数据,采用皮尔逊相关系数和回归分析模型,对风灾事故等两变量之间存在中等偏强的正相关关系统计指标应予以提级统计,作为重点预防性指标,细化分类考核监控。对总量不具有统计学上显著性影响或仅存中强正相关关系的水工作业安全事故、非工作状态人员死亡、失踪事故应予降级统计合并分类考察。探讨事故分级分类统计必要性,以便通过系统数据分析采取针对性监管措施。